Preference Model open-sources Karotte, the RL environment framework hardened over 1M+ eval runs
jamdac · x · 2026-10-08
Preference Model (founded by Jennifer Zhou and Ning Cao) has open-sourced Karotte, the framework it used over the past year to build ML-engineering RL environments for frontier labs.
- RL environments live or die on graders, since models relentlessly try to game them; Karotte bakes in defenses hardened through 1M+ evaluation runs and red-teaming to keep models on real tasks instead of loopholes.
- The team's next target is ML engineering itself — the hardest domain to build environments for and the one every lab wants.
Related event: a16z Backs Preference Model, Which Open-Sources RL Framework Karotte(3 posts)→
More from coding & agent
- Handwritten text, AI-built interactions: a new golden age of technical explainers — srush_nlp · 2026-10-08
- Coinbase Institute paper: stablecoins fit agent-to-agent micropayments in AiFi era — MurrLincoln · 2026-10-08
- Depth2Depth fuses DepthAnything with RealSense for dense, metric depth maps — chrismatthieu · 2026-10-08
- 12 things engineers miss since coding died: faster models, busier teams, lost satisfaction — rseroter · 2026-10-08
- Microsoft's MAI-Code-1.1-Flash goes local in GitHub Copilot with free on-device calls — flngr · 2026-10-08
- Game dev pushes back on one-shot AI hype: real winners still iterate for months — IanArawjo · 2026-10-08